Agentstore
Listed|
Install on your platform
Showing OpenClaw.
- 1
Run this in your terminal
terminal$
What we know about this skill
Publisher
techgangboss
Taken from the source listing. We haven't verified who controls this account.
Install target
Live repository
Not pinned. Installing fetches whatever the repository holds at the time you run the command.
Automated safety checks
This skill failed 1 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.
Declares what it does: failed
SKILL.md frontmatter is missing name.
SKILL.md exists, its frontmatter parses, and it declares a name and a description.
No undeclared network calls: passed
Makes no network calls.
Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.
No obfuscated payloads: passed
No encoded or obfuscated payloads.
No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.
No credential access: passed
Reads no keys, tokens, keychains or credential files.
Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.
No pipe-to-shell installers: passed
No pipe-to-shell or download-and-run installers.
No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.
Pinned to a commit: passed
Scanned techgangboss/agentstore at 0a073f0eb3.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.
- Commit
- 0a073f0eb3
- Scanned
- 1 file, 89 lines
About this skill
What it does
AgentStore allows AI agents to persistently store and retrieve data across multiple sessions. It provides a simple key-value storage mechanism, enabling agents to remember information like user preferences, ongoing task states, or previously accessed files. This functionality is crucial for building agents that maintain context and provide personalized experiences over time.
When to use it
- Remembering User Preferences: An agent can store a user's preferred language or display settings using AgentStore.
- Tracking Task Progress: A complex task, like generating a report, can be broken down into steps, with the current step stored in AgentStore so the agent knows where to resume.
- Maintaining Conversation Context: While not a replacement for full conversation memory, AgentStore can hold key pieces of information from earlier interactions.
- Storing File Paths: An agent that manages files could store paths to recently accessed documents using this skill.
Key capabilities
- Key-value storage
- Persistent data across sessions
- Simple API for storing and retrieving data
- Supports string values (other types may be supported in future versions)
Example prompts
- "Store the user's preferred language as 'en'."
- "Retrieve the value associated with the key 'current_step'."
- "What is stored under the key 'report_file_path'?"
Tips & gotchas
AgentStore currently only supports string values. Attempting to store other data types may result in errors or unexpected behavior. Consider using a more robust database solution if you need to manage complex data structures.